[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-137138-105":59,"doc-detail-137138-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","murim-multidimensional-reputation-based-incentive-mechanism-for-federated-learning","MURIM - Multidimensional Reputation-based Incentive Mechanism for Federated Learning","","Federated Learning (FL) enables collaborative model training without sharing raw data, yet it faces weak client incentives, privacy risks, and resource constraints alongside fairness requirements. MURIM proposes a multidimensional reputation-based incentive mechanism that jointly evaluates client reliability, privacy, resource capacity, and fairness, while preventing malicious or unreliable clients from receiving undeserved rewards. It allocates incentives using client contribution, latency, and reputation via a reliability verification module. Experiments on MNIST, FMNIST, and ADULT show up to 18% fairness gains, 5–9% lower privacy attack success, and up to 85% improved robustness against poisoning and noisy-gradient attacks, preserving stable convergence.",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/murim-multidimensional-reputation-based-incentive-mechanism-for-federated-learning/137138/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/murim-multidimensional-reputation-based-incentive-mechanism-for-federated-learning/137138.png","ImageObject",300,407,{"name":92,"@type":93},"วิน","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-17","2026-08-22",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",14,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What problem does MURIM address in federated learning?","Question",{"text":113,"@type":114},"MURIM targets weak client incentives, privacy and inference/poisoning risks, resource constraints, and fairness issues. It aims to ensure fair incentive allocation while discouraging malicious or unreliable clients from earning rewards.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How does MURIM decide client incentives?",{"text":118,"@type":114},"MURIM allocates incentives based on client contribution, latency, and reputation, supported by a reliability verification module. It also jointly considers privacy, resource capacity, and fairness to produce trustworthy and equitable participation.",{"name":120,"@type":111,"acceptedAnswer":121},"What performance improvements does MURIM report in experiments?",{"text":122,"@type":114},"On MNIST, FMNIST, and ADULT, MURIM shows up to 18% improvement in fairness metrics, reduces privacy attack success rates by 5–9%, and improves robustness against poisoning and noisy-gradient attacks by up to 85% versus state-of-the-art baselines.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},137138,1787400521,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":130,"read_time":41},2336475104736,"https://ap-avatar.wpscdn.com/avatar/22000c4c5e0e5b17e70?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786591360781797222","arXiv :2512 . 13955v1 [ cs .AI] 15 Dec 2025  \nMURIM: Multidimensional Reputation-based Incentive Mechanism for Federated Learning  \nSindhuja Madabushi, Dawood Wasif, and Jin-Hee Cho  \nVirginia Tech  \n{msindhuja,dawoodwasif,[jicho}@vt.edu](jicho}@vt.edu)  \nAbstract. Federated Learning (FL) has emerged as a leading privacypreserving machine learning paradigm, enabling participants to share model updates instead of raw data. However, FL continues to face key challenges, including weak client incentives, privacy risks, and resource constraints. Assessing client reliability is essential for fair incentive allocation and ensuring that each client’s data contributes meaningfully to the global model. To this end, we propose MURIM, a MUlti-dimensional Reputation-based Incentive Mechanism that jointly considers client reliability, privacy, resource capacity, and fairness while preventing malicious or unreliable clients from earning undeserved rewards. MURIM allocates incentives based on client contribution, latency, and reputation, supported by a reliability verification module. Extensive experiments on MNIST, FMNIST, and ADULT Income datasets demonstrate that MURIM achieves up to 18% improvement in fairness metrics, reduces privacy attack success rates by 5–9%, and improves robustness against poisoning and noisy-gradient attacks by up to 85% compared to state-of-the-art baselines. Overall, MURIM effectively mitigates adversarial threats, promotes fair and truthful participation, and preserves stable model convergence across heterogeneous and dynamic federated settings.  \nKeywords: Federated Learning · Incentives · Fairness · Trust and Reputation 1 Introduction  \nFederated Learning (FL) is a distributed machine learning (ML) paradigm in which multiple clients, such as mobile devices, edge servers, or organizations, collaboratively train a shared ML or Deep Learning (DL) model without exchanging raw data. In each round, a central server coordinates training by selecting a subset of clients, distributing the current global model, and aggregating locally trained updates, typically via weighted averaging, until convergence. As such, FL has become a leading privacy-preserving ML framework, widely adopted by both academia and industry. Despite its promise, FL continues to face major challenges related to client incentives, privacy preservation, resource constraints, and fairness. Sustaining client participation requires appropriate incentives, yet fairness issues from data heterogeneity are often addressed only at the outcome level, overlooking geometric imbalances in how diverse updates shape the global  \n2 Sindhuja Madabushi, Dawood Wasif, and Jin-Hee Cho  \nmodel. Although gradients, not raw data, are shared, they remain vulnerable to inference and poisoning attacks. Many clients also lack sufficient computational capacity for intensive local training, making truthful resource reporting essential. Prior work has explored reliability-, privacy-, or fairness-aware incentive mechanisms in isolation, but rewarding any single factor can induce harmful behaviors such as oversharing or misreporting, motivating a multidimensional mechanism that jointly integrates privacy, fairness, reliability, and resource constraints.  \nTo address these challenges, we propose MURIM, a Multidimensional Reputationbased Incentive Mechanism for FL. MURIM jointly integrates four dimensions, including privacy, resource constraints, fairness, and reliability, to incentivize clients in a manner that is trustworthy, equitable, and sustainable. Our goal is to design a robust, lightweight mechanism that avoids costly hardware solutions such as Trusted Execution Environments (TEE) or blockchain, enhances representation of underrepresented client updates, and rewards truthful participants proportionally to their contributions. Our key contributions are as follows:  \n1. We design a reliability mechanism that detects truthful clients based on consistency in privacy budgets, res","cbCaiuYQImVAkRQm","https://ap.wps.com/l/cbCaiuYQImVAkRQm","pdf",1208474,12,"English","# Introduction\n## Problem: Incentives, privacy risks, resource constraints, and fairness\n## Proposed approach: MURIM\n# Related Work: Incentive Mechanisms (IMs) for FL\n## Fairness-aware incentives\n## Privacy-preserving incentives\n# MURIM Design\n## Reliability verification module\n## Subspace Leverage Equalizer (SLE)\n## Unified incentive framework","[{\"question\":\"What problem does MURIM address in federated learning?\",\"answer\":\"MURIM targets weak client incentives, privacy and inference/poisoning risks, resource constraints, and fairness issues. It aims to ensure fair incentive allocation while discouraging malicious or unreliable clients from earning rewards.\"},{\"question\":\"How does MURIM decide client incentives?\",\"answer\":\"MURIM allocates incentives based on client contribution, latency, and reputation, supported by a reliability verification module. It also jointly considers privacy, resource capacity, and fairness to produce trustworthy and equitable participation.\"},{\"question\":\"What performance improvements does MURIM report in experiments?\",\"answer\":\"On MNIST, FMNIST, and ADULT, MURIM shows up to 18% improvement in fairness metrics, reduces privacy attack success rates by 5–9%, and improves robustness against poisoning and noisy-gradient attacks by up to 85% versus state-of-the-art baselines.\"}]","MURIM - Multidimensional Reputation-based Incentive Mechanism for Federated Learning | PDF"]